{"id":"W4319597842","doi":"10.3390/a16020095","title":"Defect Detection Methods for Industrial Products Using Deep Learning Techniques: A Review","year":2023,"lang":"en","type":"review","venue":"Algorithms","topic":"Industrial Vision Systems and Defect Detection","field":"Engineering","cited_by":284,"is_retracted":false,"has_abstract":true,"ca_institutions":"Ontario Tech University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Deep learning; Artificial intelligence; Digitization; Machine learning; Sample (material); Identification (biology); Task (project management); Pattern recognition (psychology); Computer vision; Engineering; Systems engineering","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.003771254,0.0006811779,0.002456112,0.0005788236,0.0002465025,0.0001012171,0.0002303615,0.001069959,0.000009545088],"category_scores_gemma":[0.001572348,0.0006074503,0.001040531,0.002023108,0.00002093909,0.0001444975,0.00006593698,0.001412098,0.00006425621],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005292433,"about_ca_system_score_gemma":0.0001275371,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000368135,"about_ca_topic_score_gemma":0.000002214599,"domain_scores_codex":[0.9964637,0.0007613972,0.001304422,0.000677238,0.0002509517,0.0005423382],"domain_scores_gemma":[0.9981771,0.0005946385,0.0004652756,0.0004773659,0.0001806307,0.0001049936],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000001883177,0.000003820738,1.189109e-8,0.03032058,0.0002257833,0.000003440441,0.000006990659,0.00002855427,0.00003179273,6.144908e-7,0.0003377058,0.9690388],"study_design_scores_gemma":[0.0001463665,0.0001281931,4.978152e-9,0.04745669,0.00127289,0.0001750468,0.000006816038,0.003979898,0.0003015874,0.000006806588,0.9459369,0.0005888545],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[1.52001e-7,0.7896261,0.2009008,0.00000212871,0.003479743,0.004403295,0.00001346931,0.001519221,0.00005517781],"genre_scores_gemma":[1.189024e-7,0.9731887,0.02165809,0.00001078459,0.002891444,0.001650755,0.0000666171,0.0003558162,0.0001777005],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.96845,"threshold_uncertainty_score":0.9996377,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2189905129289432,"score_gpt":0.433215070705195,"score_spread":0.2142245577762519,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}